app.py

import os
import gradio as gr
import requests
import ast
import json
import time
import pandas as pd
from datetime import datetime
from typing import List, Dict, Any, Annotated
from langgraph.graph import Graph, StateGraph
from typing_extensions import TypedDict
from openai import OpenAI
from tools import simple_search
import re

# -------------------------
# Utility helpers
# -------------------------

def override(_, new):
    return new

def merge_dicts(old: Dict, new: Dict) -> Dict:
    """Merge two dictionaries, with *new* values taking precedence."""
    return {**old, **new}

def tighten(q: str) -> str:
    """
    Strip long GAIA questions down to quoted phrases and capitalised words.
    Falls back to the original text if we strip too much.
    """
    quoted = re.findall(r'"([^"]+)"', q)
    caps   = re.findall(r'\b([A-Z0-9][\w-]{2,})', q)
    short  = " ".join(quoted + caps)
    return short or q

# -------------------------
# Environment & constants
# -------------------------

DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

# Remove logs directory creation since we're not storing logs anymore

# -------------------------
# State definition
# -------------------------

class AgentState(TypedDict):
    question: Annotated[str, override]
    current_step: Annotated[str, override]
    final_answer: Annotated[str, override]
    history: Annotated[List[Dict[str, str]], list.__add__]
    needs_search: Annotated[bool, override]
    search_query: Annotated[str, override]
    task_id: Annotated[str, override]
    logs: Annotated[Dict[str, Any], merge_dicts]

# -------------------------
# BasicAgent implementation
# -------------------------

class BasicAgent:
    def __init__(self):
        if not OPENAI_API_KEY:
            raise EnvironmentError("OPENAI_API_KEY not set")
        self.llm = OpenAI(api_key=OPENAI_API_KEY)
        self.workflow = self._build_workflow()

    # ---- Low‑level LLM call
    def _call_llm(self, prompt: str, max_tokens: int = 256) -> str:
        resp = self.llm.chat.completions.create(
            model="gpt-3.5-turbo",
            messages=[
                {"role": "system", "content": "You are a careful reasoning assistant."},
                {"role": "user", "content": prompt},
            ],
            temperature=0.3,
            max_tokens=max_tokens,
        )
        return resp.choices[0].message.content.strip()

    # ---- Workflow nodes
    def _analyze_question(self, state: AgentState) -> AgentState:
        prompt = (
            "You will receive a user question. Think step‑by‑step to decide whether external web search is required. "
            "Respond ONLY with a valid Python dict literal in the following format and NOTHING else:\n"
            "{\n  'needs_search': bool,\n  'search_query': str\n} \n\n"
            f"Question: {state['question']}"
        )
        raw = self._call_llm(prompt)
        try:
            decision = ast.literal_eval(raw)
            state["needs_search"] = bool(decision.get("needs_search", False))
            state["search_query"] = decision.get("search_query", state["question"])
        except Exception:
            # fallback: assume search needed
            state["needs_search"] = True
            state["search_query"] = state["question"]
            decision = {"parse_error": raw}
        state["logs"] = {
            "analyze": {"prompt": prompt, "llm_response": raw, "decision": decision}
        }
        state["current_step"] = "search" if state["needs_search"] else "answer"
        state["history"].append({"step": "analyze", "output": decision})
        return state

    def _perform_search(self, state: AgentState) -> AgentState:
        results = simple_search(state["search_query"], max_results=5)
        print("\nSearch Results:")
        for i, s in enumerate(results, 1):
            print(f"[{i}] {s[:120]}…")
        state["history"].append({"step": "search", "results": results})
        state["logs"]["search"] = {"query": state["search_query"], "results": results}
        state["needs_search"] = not results  # Set to True if no results found
        state["current_step"] = "recheck"
        return state

    def _re_evaluate(self, state: AgentState) -> AgentState:
        """If search returned nothing, reformulate a shorter query."""
        if state["needs_search"]:
            state["search_query"] = tighten(state["question"])
            state["current_step"] = "search"
        else:
            state["current_step"] = "answer"
        return state

    def _extract_boxed_answer(self, text: str) -> str:
        """Extract answer from boxed format or return original text if no box found."""
        # Look for text between [box] and [/box] tags
        box_match = re.search(r'\[box\](.*?)\[/box\]', text, re.DOTALL)
        if box_match:
            return box_match.group(1).strip()
        return text.strip()

    def _generate_answer(self, state: AgentState) -> AgentState:
        # Get the last search results
        search_block = "\n".join(state["history"][-1]["results"])  # last search step
        
        prompt = f"""
You are an expert fact-extractor. Using ONLY the text below, answer the question.

Question:
{state['question']}

Search snippets (bold terms are highlighted):
{search_block}

Think step-by-step. Quote exact numbers/names if needed.
END EACH STEP with ➤.  After reasoning, output:

ANSWER: <the short answer here>

No other text.
"""
        raw = self._call_llm(prompt, 300)
        answer = raw.splitlines()[-1].replace("ANSWER:", "").strip()
        
        state["final_answer"] = answer
        state["history"].append({"step": "answer", "output": raw})  # Store full response for debugging
        state["logs"]["final_answer"] = {"prompt": prompt, "response": raw}
        state["current_step"] = "done"
        return state

    # ---- Build LangGraph workflow
    def _build_workflow(self) -> Graph:
        sg = StateGraph(state_schema=AgentState)
        sg.add_node("analyze", self._analyze_question)
        sg.add_node("search", self._perform_search)
        sg.add_node("recheck", self._re_evaluate)
        sg.add_node("answer", self._generate_answer)

        # transitions
        sg.add_edge("analyze", "search")
        sg.add_edge("analyze", "answer")
        sg.add_edge("search", "recheck")

        def router(state: AgentState):
            return state["current_step"]

        sg.add_conditional_edges("analyze", router, {"search": "search", "answer": "answer"})
        sg.add_conditional_edges("recheck", router, {"search": "search", "answer": "answer"})
        sg.set_entry_point("analyze")
        sg.set_finish_point("answer")
        return sg.compile()

    # ---- Public call
    def __call__(self, question: str, task_id: str = "unknown") -> str:
        state: AgentState = {
            "question": question,
            "current_step": "analyze",
            "final_answer": "",
            "history": [],
            "needs_search": False,
            "search_query": "",
            "task_id": task_id,
            "logs": {},
        }
        final_state = self.workflow.invoke(state)
        return final_state["final_answer"]

# ----------------------------------------------------------------------------------
# Gradio Interface & Submission Routines
# ----------------------------------------------------------------------------------

def run_and_submit_all(profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the BasicAgent on them, submits all answers,
    and displays the results.
    """
    # --- Determine HF Space Runtime URL and Repo URL ---
    space_id = os.getenv("SPACE_ID")
    print("Space ID: ", space_id)
    if profile:
        username = f"{profile.username}"
        print(f"User logged in: {username}")
    else:
        print("User not logged in.")
        return "Please Login to Hugging Face with the button.", None

    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent
    try:
        print("Initializing agent...")
        agent = BasicAgent()
        print("Agent initialized successfully.")
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None

    # In the case of an app running as a hugging Face space, this link points toward your codebase
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(f"Agent code location: {agent_code}")

    # 2. Fetch Questions
    print(f"Fetching questions from: {questions_url}")
    try:
        response = requests.get(questions_url, timeout=15)
        response.raise_for_status()
        questions_data = response.json()
        if not questions_data:
            print("Fetched questions list is empty.")
            return "Fetched questions list is empty or invalid format.", None
        print(f"Fetched {len(questions_data)} questions.")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching questions: {e}", None
    except requests.exceptions.JSONDecodeError as e:
        print(f"Error decoding JSON response from questions endpoint: {e}")
        print(f"Response text: {response.text[:500]}")
        return f"Error decoding server response for questions: {e}", None
    except Exception as e:
        print(f"An unexpected error occurred fetching questions: {e}")
        return f"An unexpected error occurred fetching questions: {e}", None

    # 3. Run your Agent
    results_log = []
    answers_payload = []
    print(f"Running agent workflow on {len(questions_data)} questions...")
    
    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue

        try:
            print(f"\nProcessing question {task_id}: {question_text[:50]}...")
            
            # Initialize state for this question
            state: AgentState = {
                "question": question_text,
                "current_step": "analyze",
                "final_answer": "",
                "history": [],
                "needs_search": False,
                "search_query": "",
                "task_id": task_id,
                "logs": {},
            }
            
            # Run the workflow
            final_state = agent.workflow.invoke(state)
            answer = final_state["final_answer"]
            
            # Format logs for display
            logs_text = json.dumps(final_state["logs"], indent=2)
            
            # Add to results
            answers_payload.append({"task_id": task_id, "submitted_answer": answer})
            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "Submitted Answer": answer,
                "Processing Logs": logs_text
            })
            
            print(f"Completed question {task_id}")
            
        except Exception as e:
            print(f"Error running agent on task {task_id}: {e}")
            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "Submitted Answer": f"ERROR: {e}",
                "Processing Logs": f"Error occurred: {str(e)}"
            })

    if not answers_payload:
        print("Agent did not produce any answers to submit.")
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    # 4. Prepare Submission 
    submission_data = {
        "username": username.strip(),
        "agent_code": agent_code,
        "answers": answers_payload
    }
    status_update = f"Agent workflow finished. Submitting {len(answers_payload)} answers for user '{username}'..."
    print(status_update)

    # 5. Submit
    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
    try:
        response = requests.post(submit_url, json=submission_data, timeout=60)
        response.raise_for_status()
        result_data = response.json()
        final_status = (
            f"Submission Successful!\n"
            f"User: {result_data.get('username')}\n"
            f"Overall Score: {result_data.get('score', 'N/A')}% "
            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
            f"Message: {result_data.get('message', 'No message received.')}"
        )
        print("Submission successful.")
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except requests.exceptions.HTTPError as e:
        error_detail = f"Server responded with status {e.response.status_code}."
        try:
            error_json = e.response.json()
            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
        except requests.exceptions.JSONDecodeError:
            error_detail += f" Response: {e.response.text[:500]}"
        status_message = f"Submission Failed: {error_detail}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.Timeout:
        status_message = "Submission Failed: The request timed out."
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.RequestException as e:
        status_message = f"Submission Failed: Network error - {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**

        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.

        ---
        **Disclaimers:**
        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    results_table = gr.DataFrame(
        label="Questions and Agent Answers", 
        wrap=True,
        column_widths=["10%", "30%", "30%", "30%"]  # Adjust column widths for better display
    )

    run_button.click(
        fn=run_and_submit_all,
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    # Check for SPACE_HOST and SPACE_ID at startup for information
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID")

    if space_host_startup:
        print(f"✅ SPACE_HOST found: {space_host_startup}")
        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
    else:
        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")

    if space_id_startup:
        print(f"✅ SPACE_ID found: {space_id_startup}")
        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
    else:
        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")

    print("-"*(60 + len(" App Starting ")) + "\n")

    print("Launching Gradio Interface for Basic Agent Evaluation...")
    demo.launch(debug=True, share=False)